ClawAudit verdict

skill-deep-audit

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Read-only skill quality auditor explicitly prohibiting execution of audited skill write operations; process_exec runs analysis tools only.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

38
security
60
transparency
70
maintenance

Findings (5)

Pattern match high

Pipe to bash — executes piped content as shell commands

references/check-rules.md · prose · downgraded · |bash

Pattern match high

Writes to SKILL.md — self-modifying skill

references/check-rules.md · prose · downgraded · SKILL.md write

Pattern match medium

subprocess execution — runs system commands from Python

references/check-rules.md · prose · downgraded · subprocess.run(

Pattern match medium

Instructs covert action — may act without user awareness

references/check-rules.md · prose · downgraded · silently

Pattern match low

Python os.environ.get — reads environment variable

references/check-rules.md · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

process_exec

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API